Computer Science – Computation and Language
Scientific paper
1996-04-12
Conference on Empirical Methods in Natural Language Processing (EMNLP-96), 92-100
Computer Science
Computation and Language
10 pages, 1 Postscript figure. To Appear in Proceedings of the Conference on Empirical Methods in Natural Language Processing,
Scientific paper
We describe an implemented system for robust domain-independent syntactic parsing of English, using a unification-based grammar of part-of-speech and punctuation labels coupled with a probabilistic LR parser. We present evaluations of the system's performance along several different dimensions; these enable us to assess the contribution that each individual part is making to the success of the system as a whole, and thus prioritise the effort to be devoted to its further enhancement. Currently, the system is able to parse around 80% of sentences in a substantial corpus of general text containing a number of distinct genres. On a random sample of 250 such sentences the system has a mean crossing bracket rate of 0.71 and recall and precision of 83% and 84% respectively when evaluated against manually-disambiguated analyses.
Briscoe Ted
Carroll John
No associations
LandOfFree
Apportioning Development Effort in a Probabilistic LR Parsing System through Evaluation does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Apportioning Development Effort in a Probabilistic LR Parsing System through Evaluation, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Apportioning Development Effort in a Probabilistic LR Parsing System through Evaluation will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-463900